{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:42:27Z","timestamp":1771018947049,"version":"3.50.1"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52075480"],"award-info":[{"award-number":["52075480"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2021C01008"],"award-info":[{"award-number":["2021C01008"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-level Talent Special Support Plan of Zhejiang Province","award":["2020R52004"],"award-info":[{"award-number":["2020R52004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tii.2022.3232774","type":"journal-article","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T18:50:39Z","timestamp":1673981439000},"page":"10045-10055","source":"Crossref","is-referenced-by-count":4,"title":["Hand-in-Hand Guidance: An Explore-Exploit Based Reinforcement Learning Method for Performance Driven Assembly-Adjustment"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7974-7059","authenticated-orcid":false,"given":"Guifang","family":"Duan","sequence":"first","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8698-0075","authenticated-orcid":false,"given":"Yunkun","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2463-4553","authenticated-orcid":false,"given":"Zhenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-341X","authenticated-orcid":false,"given":"Jianrong","family":"Tan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2019.101906"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSM49833.2020.9202393"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-018-2690-6"},{"key":"ref11","first-page":"332","article-title":"Look before you leap: Safe model-based reinforcement learning with human intervention","author":"xu","year":"0","journal-title":"Proc Annu Conf Robot Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2188901"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-014-0976-6"},{"key":"ref17","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref19","first-page":"2067","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","author":"saunders","year":"0","journal-title":"Proc Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref24","first-page":"181:1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"narvekar","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref23","first-page":"1","article-title":"SEED RL: Scalable and efficient deep-RL with accelerated central inference","author":"espeholt","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","first-page":"1","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-03981-1"},{"key":"ref20","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","author":"badia","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"BeBold: Exploration beyond the boundary of explored regions","author":"zhang","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3118466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074255"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.3390\/pr8111497","article-title":"Comparing reinforcement learning methods for real-time optimization of a chemical process","volume":"8","author":"quah","year":"2020","journal-title":"Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s17071692"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101839"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2710978"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2869001"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10214691\/10018503.pdf?arnumber=10018503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:17:25Z","timestamp":1693246645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10018503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":26,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tii.2022.3232774","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}